Security audit
Writing Credibility Auditor
Security checks across malware telemetry and agentic risk
Overview
This is a text-only writing-audit skill that stays within user-provided content and does not request credentials, tools, network access, persistence, or file access.
Safe to install for editorial critique of reasoning structure and credibility signals. Users should treat its output as writing-analysis guidance, not authoritative live fact-checking, because the skill itself does not verify real-world facts against current sources.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
VirusTotal findings are pending for this skill version.
Static analysis
No suspicious patterns detected.